基于软阈值降噪的脉冲卷积神经网络轴承故障诊断方法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (4398 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对工业场景下滚动轴承信号易受噪声干扰,导致故障诊断准确率低和稳定性差的问题,本文提出一种基于软阈值降噪的脉冲卷积神经网络诊断方法。该方法使用软阈值滤波去噪,运用带时间标签的卷积层处理二维信号,增强动态特征提取能力。同时,通过引入IF和LIF神经元实现对时域和频域信息的联合编码,并采用替代梯度法进行端到端训练。实验结果显示,在信噪比为6dB时,所提方法的诊断准确率达100%,在信噪比为-6dB时诊断准确率达77.33%,优于其他常用方法,表明所提方法在噪声下具有良好的诊断效果和稳定性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李浩
	黄晓峰
	邹豪杰
	孙英杰

关键词 ：故障诊断, 软阈值, 脉冲神经网络（SNN）, 替代梯度法

Abstract：The signals of rolling bearings are easily interfered by noise in industrial environments, which reduces fault diagnosis accuracy and worsens stability. This paper proposes a diagnostic method based on soft threshold denoising for spiking convolutional neural network. Soft threshold filtering for noise reduction is proposed in this paper. This paper uses time-tagged convolutional layers to process two-dimensional signals to enhance dynamic feature extraction capabilities. IF and LIF neurons are introduced to jointly encode time domain and frequency domain information, and the surrogate gradient method is used for end-to-end training. The results show that the diagnostic accuracy reaches 100% under the signal-to-noise ratio of 6dB, and still reaches 77.33% under the signal-to-noise ratio of-6dB. The results of this method have certain advantages compared with commonly used methods, which verifies that the proposed method has better diagnostic results and higher stability under noise.

Key words： fault diagnosis soft threshold spiking neural network (SNN) surrogate gradient method

收稿日期: 2023-10-08

基金资助:湖南省自然科学基金（2022JJ50088、2023JJ50198）

作者简介: 李浩（1998—）,男,安徽省合肥市人,硕士研究生,主要从事基于深度学习的轴承故障诊断方面的研究工作。

引用本文:

李浩, 黄晓峰, 邹豪杰, 孙英杰. 基于软阈值降噪的脉冲卷积神经网络轴承故障诊断方法[J]. 电气技术, 2024, 25(2): 12-20. LI Hao, HUANG Xiaofeng, ZOU Haojie, SUN Yingjie. Bearing fault diagnosis method based on soft threshold denoising for spiking convolutional neural network. Electrical Engineering, 2024, 25(2): 12-20.

链接本文:

http://dqjs.cesmedia.cn/CN/Y2024/V25/I2/12

[1] CHEN Xuefeng, WANG Shibin, QIAO Baijie, et al.Basic research on machinery fault diagnostics: past, present, and future trends[J]. Frontiers of Mechanical Engineering, 2018, 13(2): 264-291.
[2] 张军军, 陈果, 卢应强, 等. 风电场主设备预警诊断系统设计与开发[J]. 电气技术, 2023, 24(5): 52-57.
[3] 李兵, 梁舒奇, 单万宁, 等. 基于改进正余弦算法优化堆叠降噪自动编码器的电机轴承故障诊断[J]. 电工技术学报, 2022, 37(16): 4084-4093.
[4] 李志川, 兰生, 魏柯. 基于MRSVD-GRU的混合三端特高压直流输电线路单极接地故障定位方法[J]. 电气技术, 2023, 24(3): 1-8, 63.
[5] 邬春明, 朱海潮, 马欣, 等. 两级混淆对抗域自适应网络轴承故障诊断[J]. 北京交通大学学报, 2022, 46(5): 159-166.
[6] 宋向金, 孙文举, 刘国海, 等. 深度子领域自适应网络电机滚动轴承跨工况故障诊断[J]. 电工技术学报, 2024, 39(1): 182-193.
[7] 涂彦昭, 高伟, 杨耿杰. 一种基于卷积神经网络和长短期记忆网络的光伏系统故障辨识方法[J]. 电气技术, 2022, 23(2): 48-54.
[8] TANG Shengnan, ZHU Yong, YUAN Shuoqi.Intel-ligent fault diagnosis of hydraulic piston pump based on deep learning and Bayesian optimization[J]. ISA Transactions, 2022, 129: 555-563.
[9] JIN Guoqiang, ZHU Tianyi, AKRAM M W, et al.An adaptive anti-noise neural network for bearing fault diagnosis under noise and varying load conditions[J]. IEEE Access, 2020, 8: 74793-74807.
[10] 张辉, 戈宝军, 韩斌, 等. 基于GAF-CapsNet的电机轴承故障诊断方法[J]. 电工技术学报, 2023, 38(10): 2675-2685.
[11] QIAO Meiying, YAN Shuhao, TANG Xiaxia, et al.Deep convolutional and LSTM recurrent neural networks for rolling bearing fault diagnosis under strong noises and variable loads[J]. IEEE Access, 2020, 8: 66257-66269.
[12] YAO Dechen, LIU Hengchang, YANG Jianwei, et al.A lightweight neural network with strong robustness for bearing fault diagnosis[J]. Measurement, 2020, 159: 107756.
[13] 蔡超志, 白金鑫, 池耀磊, 等. 基于CEEMDAN自适应小波降噪与卷积神经网络的齿轮箱故障诊断研究[J]. 机床与液压, 2022, 50(24): 171-180.
[14] HE Chao, SHI Hongmei, SI Jin, et al.Physics-informed interpretable wavelet weight initialization and balanced dynamic adaptive threshold for intelligent fault diagnosis of rolling bearings[J]. Journal of Manufacturing Systems, 2023, 70: 579-592.
[15] ROY K, JAISWAL A, PANDA P.Towards spike-based machine intelligence with neuromorphic computing[J]. Nature, 2019, 575(7784): 607-617.
[16] ZUO Lin, ZHANG Lei, ZHANG Zhehan, et al.A spiking neural network-based approach to bearing fault diagnosis[J]. Journal of Manufacturing Systems, 2021, 61: 714-724.
[17] NEFTCI E O, MOSTAFA H, ZENKE F.Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks[J]. IEEE Signal Processing Magazine, 2019, 36(6): 51-63.
[18] FANG Wei, YU Zhaofei, CHEN Yanqi, et al.Incorporating learnable membrane time constant to enhance learning of spiking neural networks[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 2022: 2641-2651.
[19] MAGAR R, GHULE L, LI Junhan, et al.FaultNet: a deep convolutional neural network for bearing fault classification[J]. IEEE Access, 2021, 9: 25189-25199.
[20] ZHANG Changfan, XIAO Zunguang, SHENG Zhenwen. A bearing fault diagnosis method based on a convolutional spiking neural network with spatial-temporal feature-extraction capability[J]. Transporta-tion Safety and Environment, 2023, 5(2): tdac050.